Provides introductions and tutorials on Bilibili-related technologies.
This article details how Bilibili’s multimedia lab leveraged a multimodal training pipeline combining data‑compressed SFT and the GRPO reinforcement‑learning algorithm to achieve a 13.5% metric boost and secure second place in the ICCV MIPI Detailed Image Quality Assessment competition.
VibeCut introduces a novel Orchestrator‑Executor dual‑agent framework for WebCut, leveraging large language models, shared structured context, and modular tool integration to automate complex video editing tasks, demonstrating improved efficiency, transparency, and adaptability across diverse scenarios while addressing challenges of multi‑agent coordination.
This article explains how Retrieval‑Augmented Generation (RAG) combines large language models with vector databases to let non‑technical staff query massive membership data using plain language, detailing the workflow, technical architecture, optimization challenges, and real‑world impact on data‑driven decision making.
TextFlux introduces an OCR‑free diffusion‑based framework that seamlessly inserts multilingual text into real‑world images using only glyph images and minimal training data, offering high visual fidelity, zero‑shot character rendering, and efficient multi‑line and single‑line generation on consumer GPUs.
This article details a deep engineering effort that transforms Kotlin Multiplatform on iOS into a first‑class development environment, covering the current pain points, root causes, a redesigned Bazel‑based build pipeline, parallel compilation techniques, performance gains, and future roadmap for mobile developers.
AniME introduces a director‑driven multi‑agent system that combines a custom model‑selection protocol (MCP) with the open‑source AniSora V3 model to automatically generate consistent, high‑quality long‑form animation from story scripts, handling everything from storyboard creation to video editing and quality evaluation.
The article examines why a TLS 1.3 upgrade still exhibited a two‑RTT handshake, traces the extra round‑trip to TCP’s Nagle algorithm, and shows how disabling it restores the expected one‑RTT performance while highlighting the interplay between TLS and lower‑layer protocols.
This article details Bilibili's third‑generation streaming transcoding system, explaining its architecture, core modules, testing strategies, quality‑assurance plans, and code examples that together dramatically reduce processing time and support millions of daily video uploads.
This article explains the technical challenges and innovative AI solutions behind preserving speaker identity, emotion, and timing while translating video content into multiple languages, covering speech generation modeling, speaker segmentation, adversarial reinforcement learning, proper‑noun adaptation, and audio‑visual alignment techniques.
This article details Bilibili's multi-layer storage architecture and Alluxio‑based cache acceleration for large‑scale AI model training, covering challenges of high‑throughput, low‑latency file access, metadata scalability, fault tolerance, and the engineering solutions that boosted I/O performance up to ten‑fold.
